agentleFS
Sign inStart free
barakgutbarakgut/llm-wiki/skills/wiki-query/SKILL.md

wiki-query

Skill1 starsChanged 32 days agoMITView on GitHub

Answer a question from the wiki with citations and, once the user confirms the answer, file valuable answers back as analysis pages. Use when the user asks what the wiki/their notes/sources say, asks to compare, summarize, trace or explain something covered by the wiki, or asks for a table, deck or chart built from it.

41 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use wiki-capture, wiki-update and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • jehrhardtSkill

    wiki-capture

    Quickly capture raw thoughts, links, images, or notes to today's Obsidian daily note from anywhere in Pi. Use when the user wants to jot something down for later wiki processing.

    Also in 6 projects that use this

  • bozhouDevSkill

    wiki-update

    Use when revising existing wiki pages because knowledge has changed, a new piece of information updates or contradicts existing content, or the user wants to directly edit wiki content with LLM assistance.

    Also in 9 projects that use this

  • Ivy-Chen1999Skill

    wiki-setup

    Initialize a new Obsidian wiki vault with the correct structure, special files, and configuration. Use this skill when the user wants to set up a new wiki from scratch, initialize the vault structure, create the .env file, or says things like "set up my wiki", "initialize obsidian", "create a new vault", "get started with the wiki". Also use when the user needs to reconfigure their existing vault or fix a broken setup.

    Also in 5 projects that use this

  • Ivy-Chen1999Skill

    wiki-research

    Autonomously research a topic via multi-round web search, synthesize findings, and file structured results into the Obsidian wiki. Use this skill when the user says "/wiki-research [topic]", "research X", "find everything about Y", "do a deep dive on Z", "autonomous research on X", or wants comprehensive, web-sourced knowledge on a topic filed directly into their wiki.

    Also in 4 projects that use this

  • justvinhhereSkill

    wiki-review

    Use when the user runs /review, says "show pending changes", "what's uncommitted", or wants an audit of uncommitted wiki edits before they land in history. Narrates uncommitted changes, flags structural issues scoped to those changes, and commits them with a conventional subject. Fully automatic.

    Also in 8 projects that use this

  • nathanadaySkill

    almagest

    Orient in the Almagest vault, say what waits for the user, do the work a request asks in a linked repository, and route any other request to the skill that owns it. Use for /almagest, what is going on, status, what waits for me, where do I work on X, work on X, fix this, implement, build, note this, remember to, publish my journal, what is in my journals, and any request when the right skill is not clear. Keeping part of this conversation is wiki-save; files to learn from are wiki-ingest.

    Also in 3 projects that use this

  • +5 more from Ivy-Chen1999

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Answer: Every wiki-backed claim carries its [[slug]].

    line 18

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Query

The wiki is the first stop; raw sources are the fallback; your own knowledge is labelled as such.

Paths written here (raw/…, wiki/…, AGENTS.md) are from the wiki root; the first line of llm-wiki stats says where that is. The CLI takes them as written and prints paths from the current directory: open, write and edit files by the printed form.

Main session: a lookup one search line or one page settles, answer directly. Anything wider goes to the wiki-querier subagent - give it the question and the wanted format; independent questions go to separate queriers in parallel. Relay its answer and any page edit it proposes, then do step 6 when it reports File-worthy: yes. A subagent runs steps 1-5.

  1. Split the question into the sub-questions it needs answered.
  2. Search. llm-wiki search "<terms>" per sub-question, using the entity/concept names rather than the question's phrasing. Filters: --type, --tag, -n. The result line (title + summary + best line) is usually enough to decide whether to open a page. For broad "what's in here" questions read wiki/index.md or wiki/overview.md instead.
  3. Read the top hits. Widen with llm-wiki links <slug> and read neighbours that bear on the question. Done when every sub-question has a page that answers it or is a confirmed gap.
  4. Fall back for gaps: llm-wiki search --raw "<terms>" and read the raw file at the matching line. A gap that raw sources fill means the wiki is missing something - leave the page as it is and propose the edit with the answer: the page, the text to add, the raw file and line it rests on. Make it when the user approves.
  5. Answer. Every wiki-backed claim carries its [[slug]]. Mark inference as inference and outside knowledge as not-from-the-wiki. Name the gaps. Choose the format from llm-wiki ref output-formats when the question wants a table, timeline, deck or chart.

  6. File back, once the user confirms. The wiki is written only on the user's word.

    • An answer is file-worthy when it is a synthesis the wiki did not already contain: a comparison, a connection across 3+ pages, a resolved contradiction. After such an answer ask: is this correct, and should it be filed? "file that" from the user puts the same question to any answer; "don't file" drops it.
    • The user refines: revise the answer, show it again, ask again. File the version they accept.
    • On acceptance: llm-wiki new analysis "<Title>" --summary "<the answer in one line>" --sources <slugs>, fill it, set question:. Add a [[analysis-slug]] link from each page it draws on, so it is reachable. llm-wiki lint --errors clean, then llm-wiki log query "<question>" -m "filed: <slug>".

    Lookups that restate one page are answered in chat, with no question and nothing filed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free